{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/muse-voice-transcribe-1-0/","md":"https://postcutoff.com/m/muse-voice-transcribe-1-0/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"muse-voice-transcribe-1-0","name":"Muse Voice Transcribe 1.0","org":"Meta","family":"Muse","released":"2026-09-03","status":"current","type":"audio/speech","modality_in":["audio"],"modality_out":["text"],"open_weights":false,"model_license":"proprietary","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":{"per_1k_minutes":3,"unit":"USD per 1,000 minutes of audio ($0.18/hour)","source":"https://dev.meta.ai/resources/blog/meet-muse-voice-transcribe-streaming-speech-to-text/"},"price_line":"$3 per 1,000 minutes","access":[{"provider":"Meta Model API (streaming)","model_id":"muse-voice-transcribe-1.0","endpoint":"wss://api.meta.ai/v1/asr/realtime","docs":"https://dev.meta.ai/docs/overview"},{"provider":"Meta Model API (file)","model_id":"muse-voice-transcribe-1.0","endpoint":"https://api.meta.ai/v1/asr/transcribe","docs":"https://dev.meta.ai/docs/overview"}],"capabilities":[{"name":"#1 streaming STT on Artificial Analysis (claimed)","detail":"Meta says it ranks first on the Artificial Analysis streaming speech-to-text leaderboard and had the lowest average diarization error rate among APIs tested, streaming and offline.","first":false,"discovered":"launch","source":"https://dev.meta.ai/resources/blog/meet-muse-voice-transcribe-streaming-speech-to-text/"},{"name":"Diarization, VAD and endpointing in one model","detail":"Speaker attribution for 20+ speakers, punctuation, speech-boundary detection and adaptive delay (uses more audio context only for ambiguous words).","first":false,"discovered":"launch","source":"https://dev.meta.ai/resources/blog/meet-muse-voice-transcribe-streaming-speech-to-text/"}],"entry":"2026-09-03-meta-muse-voice-transcribe","notes":"Meta's first real-time audio perception model on the Meta Model API (launched 2026-09-03); 25+ languages. Speech-to-text only: Meta does not offer a TTS or speech-to-speech API; Muse's realtime voice mode and Muse Realtime Avatar (Connect, 2026-09-23) are consumer features without a documented API.","verified":"2026-09-29","body_md":"Streaming and file transcription for voice agents built on Muse.\n\nSources: https://dev.meta.ai/resources/blog/meet-muse-voice-transcribe-streaming-speech-to-text/ · https://dev.meta.ai/docs/overview","page_url":"https://postcutoff.com/m/muse-voice-transcribe-1-0/","standing":{"kind":"speech and audio","newer_count":28,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"omnilingual-asr","name":"Omnilingual ASR","org":"Meta","released":"2025-11-10","page_url":"https://postcutoff.com/m/omnilingual-asr/"},"after":null,"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}